A Privacy-Preserving and Trustable Multi-agent Learning Framework
arXiv:2106.01242
Abstract
Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has been shown that, even when data is not directly shared, the training process is vulnerable to privacy attacks including data reconstruction and model inversion attacks. Additionally, malicious agents that train on inverted labels or random data, may arbitrarily weaken the accuracy of the global model. This paper addresses these challenges and presents Privacy-preserving and trustable Distributed Learning (PT-DL), a fully decentralized framework that relies on Differential Privacy to guarantee strong privacy protections of the agents' data, and Ethereum smart contracts to ensure trustability. The paper shows that PT-DL is resilient up to a 50% collusion attack, with high probability, in a malicious trust model and the experimental evaluation illustrates the benefits of the proposed model as a privacy-preserving and trustable distributed multi-agent learning system on several classification tasks.
arXiv commentThis paper is an extended version of Reference [32]
References in corpus (13)
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Can AI help in screening Viral and COVID-19 pneumonia?
- Renyi Differential Privacy
- COVID-19 Image Data Collection
- Federated Optimization:Distributed Optimization Beyond the Datacenter
- Differentially Private Federated Learning: A Client Level Perspective
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Distributed Constraint Optimization Problems and Applications: A Survey
- Rényi Differential Privacy of the Sampled Gaussian Mechanism
- Adding vs. Averaging in Distributed Primal-Dual Optimization
- LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
- Blockchained On-Device Federated Learning